Evolving Personalities in Chaos: An LLM-Augmented Framework for Character Discovery in the Iterated Prisoners Dilemma under Environmental Stress
Standard simulations of the Iterated Prisoners Dilemma (IPD) operate in deterministic, noise-free environments, producing strategies that may be theoretically optimal but fragile when confronted with real-world uncertainty. This paper addresses two critical gaps in evolutionary game theory research: (1) the absence of realistic environmental stressors during strategy evolution, and (2) the Interpretability Gap, where evolved genetic strategies remain opaque binary sequences devoid of semantic meaning. We introduce a novel framework combining stochastic environmental perturbations (God Mode) with Large Language Model (LLM)-based behavioral profiling to transform evolved genotypes into interpretable character archetypes. Our experiments demonstrate that strategies evolved under chaotic conditions exhibit superior resilience and present distinct behavioral phenotypes, ranging from Ruthless Capitalists to Diplomatic Enforcers. These phenotypes are readily classified by LLMs but remain nearly impossible to interpret through manual genome inspection alone. This work bridges evolutionary computation with explainable AI and provides a template for automated agent characterization in multi-agent systems.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Augmented Regression Models using Neurochaos Learning
This study presents novel Augmented Regression Models using Neurochaos Learning (NL), where Tracemean features derived from the Neurochaos Learning framework are integrated with traditional regression algorithms : Linear…
regressionDiPS: Dialogue Policy Selection for High-Stakes Persuasion Agents
Large Language Models (LLMs) often struggle with persuasion in high-stakes scenarios. People's individual personalities and concerns require tailored strategies rather than a one-size-fits-all approach. To address this c…
Augmenting Dialog with Think-Aloud Utterances for Modeling Individual Personality Traits by LLM
This study proposes augmenting dialog data with think-aloud utterances (TAUs) for modeling individual personalities in text chat by LLM. TAU is a verbalization of a speaker's thought before articulating the utterance. We…
What if Red Can Talk? Dynamic Dialogue Generation Using Large Language Models
Role-playing games (RPGs) provide players with a rich, interactive world to explore. Dialogue serves as the primary means of communication between developers and players, manifesting in various forms such as guides, NPC …
Dialogue GenerationKnowledge GraphsInCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews
Role-playing agents (RPAs), powered by large language models, have emerged as a flourishing field of applications. However, a key challenge lies in assessing whether RPAs accurately reproduce the personas of target chara…